W1

An AI coding agent that lives in your editor. Describe what you want — a feature, a fix, a whole app — and W1 works in your project: inspecting files, editing, running commands, and reporting the factual result live in the side panel.

No API keys. No setup. W1 runs on a hosted backend, so you just sign in and start building — nothing to configure, no provider keys on your machine.

🔑 Closed beta

W1 is invite-only right now. You'll need a beta key to sign in — join the waitlist at w1lab.com and we'll send you one.

What W1 does

• Builds — "add Google sign-in", "make a landing page for my app", "scaffold a REST API."
• Fixes & refactors — "find why checkout fails and fix it", "split this 800-line file into modules."
• Explains — ask how part of your codebase works; W1 reads it and tells you.
• Designs from images — paste or drop a screenshot and W1 builds to match.

Every run happens in your real project, and you watch each step as it goes.

Get started

1. Install W1 (you're here) and reload your editor.
2. Click the W1 icon in the sidebar → Sign in.
3. Paste your beta key when prompted. (No key yet? Join the waitlist.)
4. Open a folder, type what you want, and hit send.

💡 Have Node and git installed for best results — W1 can use your project commands when they are relevant — but it works without them.

Why W1

• Just sign in — no keys, no model setup, no per-token billing to wire up.
• It owns the work — one actor decides when inspection, edits, commands, or tests are useful and reports the real results.
• Native actions — structured tool calls keep file contents and command arguments separate from narration.
• Stays out of your repo — W1 keeps its working files to itself; your codebase stays clean.

Privacy

W1 runs on a hosted backend, so the request and bounded context required for inference leave your machine. Full traces stay local by default:

• Run traces — full traces are written to <workspace>/.w1/runs/ and stay local by default.
• Usage analytics — structural fields such as tokens, latency, exact status, tool names/counts, command verbs, file extensions, and hashed IDs. No prompts, code, paths, command strings, model output, or tool observations are sent to PostHog.
• Set VS Code's telemetry.telemetryLevel to off to disable both.

Full policy: app.w1lab.com/privacy

Settings

Made for builders. Join the waitlist →